CN115277459A

CN115277459A - Method and device for adjusting service quality strategy, storage medium and electronic equipment

Info

Publication number: CN115277459A
Application number: CN202210900899.7A
Authority: CN
Inventors: 曹亚平; 孙颖; 邓桓; 张会肖; 王飞飞
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2022-07-28
Filing date: 2022-07-28
Publication date: 2022-11-01

Abstract

The disclosure relates to the technical field of communication, and provides a method and a device for adjusting a quality of service policy, a computer-readable storage medium and an electronic device. Wherein, the method comprises the following steps: acquiring a current characteristic value of network service quality characteristics of a user, and inputting the current characteristic value into a network service quality data prediction model to obtain a characteristic prediction value of the network service quality characteristics; comparing the characteristic predicted value with an index required value of a network service quality index ordered by a user; and adjusting the service quality strategy of the network according to the comparison result. According to the scheme, the network service quality strategy can be adjusted based on the prediction of the characteristic value of the network service quality characteristic, so that the accuracy of the determined network service quality strategy is improved, and the utilization rate of network resources is further improved.

Description

Method and device for adjusting service quality strategy, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of communications technologies, and in particular, to a method and an apparatus for adjusting a quality of service policy, a computer-readable storage medium, and an electronic device.

Background

The fixed network and mobile network convergence technology can connect voice, unified communication, wired and wireless networks, and realize communication in the real sense.

Taking the integration of a 5G (5 th Generation Mobile Communication Technology, fifth Generation Mobile Communication Technology) Mobile network and a fixed network as an example, different network segments at the 5G Mobile network side and the fixed network side may cause a problem of inconsistency of the used qos policy, and the network may not meet the optimization adjustment of the qos policy by the flexible change of the client's own requirement index, so that the accuracy of the used qos policy is low, and further the network resources are wasted.

Therefore, how to ensure that the service quality of the end-to-end service converged by the mobile network and the fixed network can meet the dynamic change requirement of the user and can achieve reasonable utilization of resources is a problem which needs to be solved urgently at present.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure aims to provide a method and an apparatus for adjusting a qos policy, a computer-readable storage medium, and an electronic device, so as to improve a problem of low network resource utilization caused by inconsistency between qos policies of a fixed network and a mobile network in a convergence scenario at least to a certain extent.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to a first aspect of the present disclosure, there is provided a method for adjusting a quality of service policy, including: acquiring a current characteristic value of network service quality characteristics of a user, and inputting the current characteristic value into a network service quality data prediction model to obtain a characteristic prediction value of the network service quality characteristics; comparing the characteristic predicted value with an index required value of a network service quality index ordered by a user; and adjusting the service quality strategy of the network according to the comparison result.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the network quality of service characteristics include one or more of a rate, a bandwidth, a packet loss rate, a source IP address, a destination IP address, a port, a delay, and a jitter of a network.

In an exemplary embodiment of the present disclosure, based on the foregoing solution, the current feature value of the network quality of service feature includes a first current feature value and a second current feature value, and the feature prediction value of the network quality of service feature includes a first feature prediction value and a second feature prediction value; the comparing the characteristic predicted value with the index required value of the network service quality index ordered by the user comprises the following steps: determining a maximum value of the first feature prediction value and the second feature prediction value; comparing the maximum value with the index required value of the network service quality index ordered by the user; the first current characteristic value is determined according to the current characteristic value of the uplink network service quality characteristic, the second current characteristic value is determined according to the current characteristic value of the downlink network service quality characteristic, the first characteristic predicted value is determined according to the characteristic predicted value of the uplink network service quality characteristic, and the second characteristic predicted value is determined according to the characteristic predicted value of the downlink network service quality characteristic.

In an exemplary embodiment of the disclosure, based on the foregoing solution, the adjusting the quality of service policy of the network according to the comparison result includes: under the condition that the difference value between the characteristic predicted value and the index required value is larger than a preset value, adjusting a service quality strategy of the network according to the characteristic predicted value; and determining that the current service quality strategy of the network is unchanged under the condition that the difference value between the characteristic predicted value and the index required value is less than or equal to the preset value.

In an exemplary embodiment of the present disclosure, based on the foregoing solution, the adjusting the quality of service policy of the network according to the feature prediction value includes: when the current index value of the service quality index of the mobile network side is inconsistent with the characteristic predicted value, the service quality strategy of the mobile network side is adjusted according to the characteristic predicted value; and when the current index value of the service quality index of the fixed network side is inconsistent with the characteristic predicted value, adjusting the service quality strategy of the fixed network side according to the characteristic predicted value.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the obtaining a current feature value of a network quality of service feature of a user includes: and acquiring the current characteristic value of the network service quality characteristic of the user according to a preset period.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the network quality of service data prediction model is determined by: acquiring a characteristic value sequence of the acquired network service quality characteristics; preprocessing data in the characteristic value sequence to obtain training data; and training the long-term and short-term memory network according to the training data to obtain the network service quality data prediction model.

According to a second aspect of the present disclosure, an apparatus for adjusting a qos policy is provided, which includes a data prediction module configured to obtain a current feature value of a qos feature of a user, and input the current feature value into a qos data prediction model to obtain a feature prediction value of the qos feature; the data comparison module is configured to compare the characteristic predicted value with an index required value of a network service quality index ordered by a user; and the service quality strategy adjusting module is configured to adjust the service quality strategy of the network according to the comparison result.

According to a third aspect of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method of adjusting a quality of service policy as described in the first aspect of the embodiments above.

According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; and a storage device configured to store one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method for adjusting the quality of service policy according to the first aspect of the embodiments.

As can be seen from the foregoing technical solutions, the method and apparatus for adjusting a qos policy in the exemplary embodiment of the present disclosure, and the computer-readable storage medium and the electronic device for implementing the method for adjusting a qos policy have at least the following advantages and positive effects:

in the technical solutions provided in some embodiments of the present disclosure, a current feature value of a network service quality feature of a user is obtained, the current feature value is input into a network service quality data prediction model to obtain a feature prediction value of the network service quality feature, the feature prediction value is compared with an index required value of a network service quality index for ordering, and a service quality policy of a network can be adjusted according to a comparison result. Compared with the related art, on one hand, the method and the system can adjust the network service quality strategy according to the user requirement, and improve the utilization rate of network resources; on the other hand, the accuracy of the adjusted network service quality strategy can be improved by predicting the characteristic value of the network service quality characteristic.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

Fig. 1 illustrates a flow chart of a method for adjusting a quality of service policy in an exemplary embodiment of the disclosure;

FIG. 2 illustrates a flow diagram of a method of training a network quality of service data prediction model in an exemplary embodiment of the present disclosure;

FIG. 3 is a flow chart illustrating a method for comparing quality of service characteristic forecast data with quality of service characteristic demand data in an exemplary embodiment of the present disclosure;

fig. 4 is a flowchart illustrating a method for adjusting a qos policy according to a comparison result in an exemplary embodiment of the present disclosure;

FIG. 5 illustrates a schematic diagram of a quality of service policy adjustment system in an exemplary embodiment of the present disclosure;

FIG. 6 illustrates a multi-terminal interaction diagram during quality of service policy adjustment in an exemplary embodiment of the disclosure;

fig. 7 is a schematic structural diagram of a qos policy adjustment apparatus according to an exemplary embodiment of the present disclosure;

fig. 8 shows a schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

The terms "a," "an," "the," and "said" are used in this specification to denote the presence of one or more elements/components/parts/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. other than the listed elements/components/etc.; the terms "first" and "second", etc. are used merely as labels, and are not limiting on the number of their objects.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities.

Under the large background of rapid development of the 5G network, the organic fusion of the 5G network and the fixed network is also widely applied.

At present, in end-to-end 5G to B (B refers to industrial internet end, G to B is roughly divided into eight vertical industries such as industrial manufacturing, smart grid, media entertainment, medical health, car networking, smart city, smart finance, and smart education), there are problems that service policies used in different network segments of a 5G network side and a fixed network side are inconsistent, the change of network service quality cannot meet the user's requirements, and the service quality policy cannot be adjusted according to the flexible change of the user's own requirement index.

However, the existence of these problems may result in inaccurate use of network qos policies and unreasonable utilization of network resources, resulting in waste of network resources. In the embodiments of the present disclosure, a method for adjusting a quality of service policy is provided first, which overcomes, at least to some extent, the drawbacks in the related art.

Fig. 1 illustrates a method for adjusting a quality of service policy in an exemplary embodiment of the present disclosure. Referring to fig. 1, the method includes:

step S110, obtaining a current characteristic value of the network service quality characteristic of a user, inputting the current characteristic value into a network service quality data prediction model, and obtaining a characteristic prediction value of the network service quality characteristic;

step S120, comparing the characteristic predicted value with the index required value of the network service quality index ordered by the user;

step S130, according to the comparison result, the service quality strategy of the network is adjusted.

In the technical solution provided in the embodiment shown in fig. 1, a current feature value of a network service quality feature of a user is obtained, the current feature value is input into a network service quality data prediction model to obtain a feature prediction value of the network service quality feature, the feature prediction value is compared with an index required value of a network service quality index for ordering, and a service quality policy of a network can be adjusted according to a comparison result. Compared with the related art, on one hand, the method and the device can adjust the network service quality strategy according to the user requirement, and improve the utilization rate of network resources; on the other hand, the accuracy of the adjusted network service quality strategy can be improved by predicting the characteristic value of the network service quality characteristic. .

The following detailed description of the various steps in the example shown in fig. 1 is provided:

in step S110, obtaining a current feature value of a network service quality feature of a user, and inputting the current feature value into a network service quality data prediction model to obtain a feature prediction value of the network service quality feature;

in an exemplary embodiment, the network quality of service characteristics include one or more of a rate, a bandwidth, a packet loss rate, a source IP (Internet Protocol) address, a destination IP address, a port, a delay, and a jitter of the network. The ports may include source ports and/or destination ports, among others.

In an exemplary embodiment, the network quality of service features include upstream network quality of service features and downstream network quality of service features. Taking the example that the network service quality characteristics include the network rate, the network service quality characteristics include the uplink network rate and the downlink network rate.

Based on this, the current feature value of the network service quality feature includes a first current feature value and a second current feature value, where the first current feature value is determined according to the current feature value of the uplink network service quality feature, and the second current feature data is determined according to the current feature value of the downlink network service quality feature.

For example, network index data affecting network service quality may be determined as network service quality characteristics, such as uplink and downlink rates, uplink and downlink packet loss rates, uplink and downlink bandwidths, source IP, destination IP, ports, uplink and downlink delays, jitter, and the like of a network may be used as the network service quality characteristics.

Wherein, the source IP address and the destination IP address can be used to determine to which user the collected characteristic value of the network quality characteristic belongs.

In an exemplary embodiment, the User in step S110 may be understood as a Virtual Private Network User, and the feature value of the uplink Network quality of service feature and the feature value of the downlink Network quality of service feature of the User may be collected at a User VPN (Virtual Private Network) node of an N6 interface of a UPF (User Plane Function).

In an exemplary application scenario, the network quality policy adjustment method in the present disclosure may be applied in a network scenario where a mobile network and a fixed network are converged. The above-mentioned uplink network service quality characteristics may be understood as network service quality characteristics of the mobile network side, and the downlink network service quality characteristics may be understood as network service quality characteristics of the fixed network side.

Taking the mobile network as a 5G network as an example, the feature value of the uplink network service feature comes from the 5G terminal side, and the feature value of the downlink network service feature comes from the fixed network side client intranet.

Illustratively, the obtaining the current feature value of the network quality of service feature of the user includes: and acquiring the current characteristic value of the network service quality characteristic of the user according to the preset period.

The preset period may be determined by user-defined according to user requirements, such as a week, a month, and the like, and this is not particularly limited in this exemplary embodiment.

In other words, in the present disclosure, the feature value of the network qos feature may be predicted according to a preset period, so as to obtain a feature prediction value of each network qos feature, and determine whether to adjust the network qos policy according to the feature prediction value in a subsequent step.

For example, the network service quality data prediction model may be obtained by training in advance, and then the feature prediction value of the network service quality feature may be obtained based on the current feature value and the network service quality data prediction model. Fig. 2 shows a flowchart of a method for training a network quality of service data prediction model in an exemplary embodiment of the present disclosure, and referring to fig. 2, the method may include steps S210 to S230. Wherein:

in step S210, a feature value sequence of the collected network quality of service features is obtained.

In an exemplary embodiment, a sequence of eigenvalues of a network quality of service characteristic may be collected. The characteristic value sequence of the network service quality characteristic can be acquired according to a preset acquisition frequency. The preset sampling frequency may be customized according to a user requirement, such as real-time acquisition, or acquisition once every hour or once every day, and the like, and this is not particularly limited in this exemplary embodiment.

For example, for each network quality of service feature, a feature value of the network quality of service feature may be collected to generate a feature value sequence of the network quality of service feature. As described above, by monitoring the VPN node at the N6 interface of the UPF, the sequence of characteristic values of network service quality characteristics, such as the network rate, the packet loss rate, the source IP address, the destination IP address, the time delay, and the jitter, of the user can be obtained.

In step S220, the data in the feature value sequence is preprocessed to obtain training data.

For example, the preprocessing may include processing the data in the feature value sequence into a format suitable for machine learning model processing, such as normalizing the data in the feature value sequence, converting different input values into dimensionless data of the same order of magnitude, and so on, thereby obtaining training data.

Next, in step S230, a long-short term memory network is trained according to the training data to obtain the network quality of service data prediction model.

In an exemplary embodiment, the network quality of service data prediction model in the present disclosure may include an LSTM (Long Short-Term Memory network). Of course, the network qos data prediction model in the present disclosure may also include other prediction models, such as RNN (recurrent neural network), and the like, and this is not limited in this exemplary embodiment.

Taking the LSTM as an example of the network qos data prediction model, the training data may be divided into a training set and a test set, and the time step in the LSTM is set as a prediction period. The prediction period may be understood as the preset period described above, or the time step may be set to other lengths, which is not particularly limited in this exemplary embodiment, for example, the time step is set to 3 preset periods, that is, the feature value in the 3 history periods is used to predict the feature value of the next period.

The preset acquisition frequency mentioned in step S210 is less than or equal to the preset period. When the preset acquisition frequency is less than the preset period, the characteristic values within the preset period length can be averaged to obtain a historical characteristic value sequence. If the preset collection frequency is every day, the preset period is one week, and the characteristic values of the past 100 weeks are collected, averaging the characteristic values collected every week to obtain a historical characteristic value sequence. And when the preset acquisition frequency is equal to the preset period, determining the historical characteristic sequence according to the acquired historical characteristic value. The length of the sequence of historical eigenvalues is determined from the time step in the LSTM network.

For example, 80% of the training data may be determined as data in the training set and 20% of the training data may be determined as data in the test set. And then training the long-term and short-term memory network by using the data in the training set, optimizing parameters in the model, drawing a change diagram of the model evaluation index in the training process, and stopping training when the optimization effect of the evaluation index of the model evaluation index change diagram is not obvious. The model is then tested using the data in the test set. And when the model test result meets the preset requirement, determining the long-term and short-term memory network obtained by current training as the network service quality data prediction model in the disclosure.

Through the steps S210 to S230, a network service quality data prediction model can be obtained, so that the feature value of the network service quality feature can be predicted according to the current feature value of the network service quality feature and the network service quality data prediction model.

In an exemplary embodiment, the current feature value may be understood as an average value of features acquired in a current period, and may also be understood as a sequence containing feature values corresponding to the current period. The length of the sequence is determined according to the length of the time step of the LSTM network.

And when the step length in the LSTM network is larger than 1, the current characteristic value is a characteristic value sequence containing the characteristics acquired in the current period. When the step size in the LSTM network is equal to 1, then the current feature value may be understood as the feature value collected in the current period.

For example, the current feature value may be input into a network service quality data prediction model, so as to determine a feature prediction value of the network service quality feature according to an output result of the model.

In an exemplary embodiment, the characteristic prediction value may include a first characteristic prediction value and a second characteristic prediction value, wherein the first characteristic prediction value is determined according to a characteristic prediction value of an uplink network service quality characteristic, and the second characteristic prediction value is determined according to a characteristic prediction value of a downlink network service quality characteristic.

That is to say, a first characteristic predicted value is obtained according to the current characteristic value of the uplink network service quality characteristic in a prediction mode, and a second characteristic predicted value is obtained according to the current characteristic value of the downlink network service quality characteristic in a prediction mode.

Next, in step S120, the feature prediction value is compared with the index requirement value of the network service quality index subscribed by the user.

In an exemplary embodiment, the network quality of service indicator subscribed by the user includes the network quality of service characteristics described above. The network quality of service indicator of the user subscription includes the network bandwidth of the user subscription, such as when the network quality of service characteristic includes the network bandwidth.

For example, fig. 3 is a flowchart illustrating a method for comparing the feature prediction data of the quality of service with the feature demand data of the quality of service in an exemplary embodiment of the disclosure. Referring to fig. 3, the method may include steps S310 to S320. Wherein:

in step S310, the maximum value of the first feature prediction value and the second feature prediction value is determined.

For example, for each network quality of service feature, a maximum value may be determined at its corresponding first feature prediction value and second feature prediction value.

Next, in step S320, the maximum value is compared with the index requirement value of the network service quality index subscribed by the user.

For example, for each network service quality characteristic and the network service quality index subscribed by the user corresponding to the network service quality characteristic, the difference value may be obtained between the maximum value of the first characteristic predicted value and the second characteristic predicted value corresponding to the network service quality characteristic and the index required value of the corresponding network service quality index, so as to obtain the comparison result of the network service quality characteristic.

With continued reference to fig. 1, in step S130, the quality of service policy of the network is adjusted according to the comparison result.

Fig. 4 is a flowchart illustrating a method for adjusting a quality of service policy according to a comparison result in an exemplary embodiment of the disclosure. Referring to fig. 4, the method may include steps S410 to S430.

In step S410, it is determined whether the difference between the feature prediction value and the index required value is greater than a preset value, if so, the process goes to step S420, and if not, the process goes to step S430.

In step S420, the qos policy of the network is adjusted according to the feature prediction value.

The specific implementation of step S420 may include: when the current index value of the service quality index of the mobile network side is inconsistent with the characteristic predicted value, the service quality strategy of the mobile network side is adjusted according to the characteristic predicted value; and when the current index value of the service quality index of the fixed network side is inconsistent with the characteristic predicted value, adjusting the service quality strategy of the fixed network side according to the characteristic predicted value.

In step S430, it is determined that the current quality of service policy of the network is not changed.

In other words, when the difference between the characteristic predicted value and the index required value is greater than a preset value, the service quality strategy of the network is adjusted according to the characteristic predicted value. And under the condition that the difference value between the characteristic predicted value and the index required value is less than or equal to the preset value, the network service quality strategy is not adjusted.

For example, for each network service quality feature and the corresponding service quality index, when the difference between the feature prediction value and the index required value is greater than a preset value, the network service quality policy may be adjusted according to the maximum value of the first feature prediction value and the second feature prediction value. If the current index value of the network service quality index at the mobile network side is different from the maximum value, the index value of the network service quality index at the mobile network side is adjusted to the maximum value, and if the current index value of the service quality index at the fixed network side is different from the maximum value, the current index value of the network service quality index at the fixed network side is adjusted to the maximum value. Therefore, the network service quality indexes of the mobile network side and the fixed network side can be consistent, and further the waste of network resources is avoided.

Taking the network service quality characteristics including the bandwidth as an example, if the first predicted value of the bandwidth is 10M, the second predicted value is 15M, the preset value is 3M, the bandwidth subscribed by the user is 20M as an example, the maximum value of the first predicted value and the second predicted value is 15M, and the difference value between the first predicted value and the bandwidth subscribed by the user and the 20M is greater than the preset value 3M, it is determined that the service quality policy of the network needs to be adjusted, and because the maximum value of the first predicted value and the second predicted value is 15M, the first preset value 10M is not consistent with the maximum value 15M, and the second preset value 15M is consistent with the maximum value 15M, the bandwidth of the mobile network side is adjusted from 10M to 15M, while the bandwidth of the fixed network side is not changed, thereby completing the adjustment of the network service quality policy.

In an exemplary embodiment, the adjustment of the network quality of service policy may be understood as adjusting an index value of the network quality of service indicator indicated by the network quality of service feature that needs to be adjusted.

According to the method and the device, the characteristic value of the network service quality characteristic corresponding to the network service quality strategy is predicted, and the network service quality strategy can be adjusted according to the prediction result, so that the network service quality strategy on the mobile network side is consistent with the network service quality strategy on the fixed network side as much as possible, the waste of network resources is reduced, and the utilization rate of the network resources is improved.

Furthermore, the method monitors the characteristic value of the network service quality characteristic, can automatically adjust the network service quality strategy according to the monitoring result, effectively solves the problem of dynamic cooperation of end-to-end network resources caused by rapid and frequent change of SLA requirements of users, reduces the complex workload caused by changing the network configuration section by section when the user requirements are changed by operators, and improves the operation and maintenance efficiency.

Furthermore, the method and the device can dynamically optimize the network service quality strategy according to the user requirement by considering the index requirement value of the network service quality index ordered by the user, and improve the accuracy of the optimization of the network service quality strategy.

Next, taking the mobile network side as a 5G mobile network as an example, fig. 5 shows a schematic diagram of a quality of service policy adjustment system in an exemplary embodiment of the present disclosure. The qos policy adjustment method and apparatus in the present disclosure may be applied to the qos policy adjustment system shown in fig. 5. Referring to fig. 5, the network qos policy adjustment system may include a customer service management subsystem 510, an end-to-end service orchestration subsystem 520, and a qos-aware optimization device 530.

The service management subsystem 510 is configured to send the index requirement value of the network service quality index subscribed by the user to the end-to-end service orchestration subsystem 520.

The qos-aware optimization device 530 is configured to monitor and collect feature values of qos characteristics of uplink and downlink networks of a user. Wherein the collection point is located at a customer VPN node of the N6 interface of the UPF. The monitored characteristic value of the uplink network service characteristic comes from a 5G mobile network, and the monitored characteristic value of the downlink network service characteristic comes from a client intranet at a fixed network side.

The qos aware optimizer 530 is further configured to periodically analyze the collected uplink and downlink network qos characteristics and the trained qos data prediction model, predict a feature prediction value of the network qos characteristics of the user in the next period, and report the predicted feature prediction value to the end-to-end service orchestration subsystem 520.

The end-to-end service orchestration subsystem 520 is configured to compare the received feature prediction value with an index requirement value of a network service quality index ordered by the user, which is sent by the client service management subsystem 510, and determine whether a network service quality policy on the 5G network side and/or the fixed network side needs to be adjusted.

If it is determined that the qos policy of the 5G network side needs to be adjusted, the end-to-end service orchestration subsystem 520 sends the latest network qos policy to an SMF (Session Management Function) network element device in the 5GC, and then sends the latest network qos policy to an AMF (Access and Mobility Management Function), a base station, and a 5G terminal through the SMF.

If the quality of service policy at the fixed network side needs to be adjusted, the end-to-end service orchestration subsystem 520 sends the latest network quality of service policy to the network management device at the fixed network side, and then sends the latest network quality of service policy to the user intranet through the network management, thereby realizing the optimization of the end-to-end service.

The 5G-CPE (Customer Premise Equipment) in fig. 5 is a Customer premises Equipment on the 5G Network side, and the STN (Switched Telecommunications Network) is a Telecommunications switching Network).

Continuing with the example that the mobile network is a 5G mobile network, fig. 6 shows a schematic diagram of multi-terminal interaction in the process of adjusting the qos policy in an exemplary embodiment of the present disclosure. Next, the interactive process shown in fig. 6 will be explained.

In step S601, the qos-aware optimizer 61 collects feature values of network qos features from the UPF 62.

For example, the qos aware optimization apparatus 61 performs traffic monitoring and acquisition on a VPN at an N6 interface of a UPF network element device of the 5GC, and acquires characteristic values of network qos characteristics such as a network rate, a packet loss rate, a source IP, a destination IP, a port, a time delay, and jitter of each detected VPN user.

In step S602, the qos-aware optimization apparatus 61 obtains a feature prediction value based on the LSTM model and the collected feature values of the network qos features.

For example, the service quality perception optimization device 61 processes the collected feature value of the network service quality feature based on the LSTM model algorithm to predict the feature prediction value of the network service quality in the next period of the client.

In step S603, the qos aware optimizer 61 reports the predicted feature value to the end-to-end service orchestration subsystem 63.

In step S604, the customer service management subsystem 64 sends the index requirement value of the network service quality index subscribed by the user to the end-to-end service orchestration subsystem 63.

In step S605, the end-to-end service orchestration subsystem 63 compares the feature prediction value with the index requirement value to obtain the latest network quality of service policy.

For example, after receiving the feature prediction value, the Service orchestration subsystem 63 compares and analyzes the feature prediction value with a requirement index ordered by the user and sent by the client Service management subsystem 64, and determines whether a network Service Quality policy of the 5G network side and/or the fixed network side needs to be adjusted, so as to generate a new latest network Service Quality policy, such as a Quality of Service (QoS) rule, a delay and packet loss rate optimization policy, that meets the requirement of the current user.

If the network service quality of the 5G network side needs to be adjusted, in step S606, the end-to-end service orchestration subsystem 63 sends the determined latest network service quality policy to the SMF network element device 65 in the 5 GC.

In step S607, the SMF transmits the received latest network quality of service policy to the 5G terminal 66.

For example, if the network service quality policy of the network side of the 5G side needs to be adjusted, the end-to-end service orchestration subsystem issues the latest network service quality policy to the SMF network element device in the 5GC, and then issues the latest network service quality policy to the AMF, the base station, and the 5G terminal through the SMF;

if the network service quality of the fixed network needs to be adjusted, in step S608, the end-to-end service orchestration subsystem 63 sends the determined latest network service quality policy to the network manager 67 of the fixed network.

For example, if the network quality of service policy of the fixed network side needs to be adjusted, the end-to-end service orchestration subsystem issues the latest policy to the network management device of the fixed network side, and then issues the latest policy to the network device of the user fixed network side through the network management device of the fixed network side.

After receiving the current network service quality strategy sent by the end-to-end service arrangement subsystem, the SMF and the fixed network side network pipe can also respectively send feedback results to the end-to-end service arrangement subsystem so as to feed back the received current network service quality strategy.

Those skilled in the art will appreciate that all or part of the steps to implement the above embodiments are implemented as a computer program executed by a CPU. When executed by the CPU, performs the functions defined by the method provided by the present invention. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.

Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the method according to exemplary embodiments of the invention and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

Fig. 7 is a schematic structural diagram illustrating an apparatus for adjusting a quality of service policy in an exemplary embodiment of the present disclosure. Referring to fig. 7, the apparatus 700 for adjusting the qos policy may include a data prediction module 710, a data comparison module 720, and a qos policy adjustment module 730. Wherein:

a data prediction module 710 configured to obtain a current feature value of a network service quality feature of a user, and input the current feature value into a network service quality data prediction model to obtain a feature prediction value of the network service quality feature;

a data comparison module 720, configured to compare the feature prediction value with an index requirement value of a network service quality index ordered by a user;

and a qos policy adjustment module 730 configured to adjust the qos policy of the network according to the comparison result.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the network service quality characteristics include one or more of a rate, a bandwidth, a packet loss rate, a source IP address, a destination IP address, a port, a delay, and a jitter of a network.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the current feature value of the network quality of service feature includes a first current feature value and a second current feature value, and the feature prediction value of the network quality of service feature includes a first feature prediction value and a second feature prediction value.

The first current characteristic value is determined according to the current characteristic value of the uplink network service quality characteristic, the second current characteristic value is determined according to the current characteristic value of the downlink network service quality characteristic, the first characteristic predicted value is determined according to the characteristic predicted value of the uplink network service quality characteristic, and the second characteristic predicted value is determined according to the characteristic predicted value of the downlink network service quality characteristic.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the data comparison module 720 may be specifically configured to: determining a maximum value of the first feature prediction value and the second feature prediction value; and comparing the maximum value with the index required value of the network service quality index ordered by the user.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the quality of service policy adjusting module 730 may be specifically configured to: under the condition that the difference value between the characteristic predicted value and the index required value is larger than a preset value, adjusting the service quality strategy of the network according to the characteristic predicted value; and determining that the current service quality strategy of the network is unchanged under the condition that the difference value between the characteristic predicted value and the index required value is less than or equal to the preset value.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the adjusting the quality of service policy of the network according to the feature prediction value includes: when the current index value of the service quality index of the mobile network side is inconsistent with the characteristic predicted value, the service quality strategy of the mobile network side is adjusted according to the characteristic predicted value; and when the current index value of the service quality index of the fixed network side is inconsistent with the characteristic predicted value, adjusting the service quality strategy of the fixed network side according to the characteristic predicted value.

In some exemplary embodiments of the disclosure, based on the foregoing embodiments, the obtaining a current feature value of a network quality of service feature of a user includes: and acquiring the current characteristic value of the network service quality characteristic of the user according to the preset period.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the network quality of service data prediction model is determined by: acquiring a characteristic value sequence of the acquired network service quality characteristics; preprocessing the data in the characteristic value sequence to obtain training data; and training the long-term and short-term memory network according to the training data to obtain the network service quality data prediction model.

The specific details of each unit in the above qos policy adjusting apparatus have been described in detail in the corresponding qos policy adjusting method, and therefore are not described herein again.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that these steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer storage medium capable of implementing the above method. On which a program product capable of implementing the above-described method of the present specification is stored. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the "exemplary methods" section above of this specification, when the program product is run on the terminal device.

Embodiments of the present disclosure may also include a program product for implementing the above method, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not so limited, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 800 according to this embodiment of the disclosure is described below with reference to fig. 8. The electronic device 800 shown in fig. 8 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present disclosure.

As shown in fig. 8, electronic device 800 is in the form of a general purpose computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one memory unit 820, a bus 830 connecting various system components (including the memory unit 820 and the processing unit 810), and a display unit 840.

Wherein the storage unit stores program code that is executable by the processing unit 810 to cause the processing unit 810 to perform steps according to various exemplary embodiments of the present disclosure as described in the "exemplary methods" section above in this specification. For example, the processing unit 810 may perform various steps as shown in fig. 1.

The storage unit 820 may include readable media in the form of volatile memory units such as a random access memory unit (RAM) 8201 and/or a cache memory unit 8202, and may further include a read only memory unit (ROM) 8203.

The storage unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment.

Bus 830 may be any of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 800, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 800 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 850. Also, the electronic device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 860. As shown, the network adapter 860 communicates with the other modules of the electronic device 800 via the bus 830. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed, for example, synchronously or asynchronously in multiple modules.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A method for adjusting a quality of service policy is characterized by comprising the following steps:

acquiring a current characteristic value of network service quality characteristics of a user, and inputting the current characteristic value into a network service quality data prediction model to obtain a characteristic prediction value of the network service quality characteristics;

comparing the characteristic predicted value with an index required value of a network service quality index ordered by a user;

and adjusting the service quality strategy of the network according to the comparison result.

2. The method according to claim 1, wherein the network qos characteristics include one or more of a rate, a bandwidth, a packet loss rate, a source IP address, a destination IP address, a port, a delay, and a jitter of a network.

3. The method according to claim 1, wherein the current feature value of the network qos feature comprises a first current feature value and a second current feature value, and the feature prediction value of the network qos feature comprises a first feature prediction value and a second feature prediction value;

the step of comparing the characteristic predicted value with the index required value of the network service quality index ordered by the user comprises the following steps:

determining a maximum value of the first feature prediction value and the second feature prediction value;

comparing the maximum value with the index required value of the network service quality index ordered by the user;

4. The method for adjusting qos policy according to claim 1, wherein the adjusting qos policy of a network according to the comparison result includes:

under the condition that the difference value between the characteristic predicted value and the index required value is larger than a preset value, adjusting a service quality strategy of the network according to the characteristic predicted value;

and under the condition that the difference value between the characteristic predicted value and the index required value is less than or equal to the preset value, determining that the current service quality strategy of the network is unchanged.

5. The method for adjusting the QoS policy of claim 4, wherein the adjusting the QoS policy of the network according to the characteristic prediction value comprises:

when the current index value of the service quality index of the mobile network side is inconsistent with the characteristic predicted value, the service quality strategy of the mobile network side is adjusted according to the characteristic predicted value;

and when the current index value of the service quality index of the fixed network side is inconsistent with the characteristic predicted value, adjusting the service quality strategy of the fixed network side according to the characteristic predicted value.

6. The method for adjusting qos policy according to claim 1, wherein said obtaining a current feature value of a network qos feature of a user comprises:

and acquiring the current characteristic value of the network service quality characteristic of the user according to a preset period.

7. The method of claim 1, wherein the network QoS data prediction model is determined by:

acquiring a characteristic value sequence of the acquired network service quality characteristics;

preprocessing data in the characteristic value sequence to obtain training data;

and training the long-term and short-term memory network according to the training data to obtain the network service quality data prediction model.

8. An apparatus for adjusting a quality of service policy, comprising:

the data prediction module is configured to acquire a current characteristic value of the network service quality characteristic of the user, and input the current characteristic value into a network service quality data prediction model to obtain a characteristic prediction value of the network service quality characteristic;

the data comparison module is configured to compare the characteristic predicted value with an index required value of a network service quality index ordered by a user;

and the service quality strategy adjusting module is configured to adjust the service quality strategy of the network according to the comparison result.

9. A computer-readable medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a method of adjusting a quality of service policy according to any one of claims 1 to 7.

10. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of adjusting quality of service policies of any one of claims 1 to 7.